I wrote a 100-topic AI engineer roadmap that runs offline, with no API key

Description and use

A 100-topic AI engineering roadmap that runs offline without API keys, covering RAG, agents, MCP, and production AI.

Problem

Learners struggled to organize and access RAG, agents, and MCP tutorials, leading to disordered learning and reliance on multiple browser tabs.

Outcome

The roadmap provides a comprehensive, offline learning path for AI engineering, reducing dependency on external APIs and streamlining study.

Workflow

• Clone the repo
• Create a virtual environment
• Install dependencies
• Run the mini RAG demo
• Explore topic folders and code examples

Evidence

Every time I wanted to learn RAG, agents or MCP properly, I ended up with twelve browser tabs and no order to read them in.

Source

ai-engineer-roadmap is 100 topics in 7 phases, from "what is RAG?" to production AI.

Source

The 7 phases are RAG Foundations (20 topics), Advanced RAG (20), LLM Concepts (14), Agentic AI (16), Frameworks (8), MCP (7) and Production AI (15).

Source

The last command runs a complete, tiny RAG pipeline. It chunks three sample documents, scores them against your question and prints the best passage with its source file.

Source

The demo scripts in each code/ folder use only the Python standard library, so there is no API key and no network needed.

Source

CI checks that every local link in the Markdown pages points to a file that exists, validates the SVG diagrams, runs the tests and builds the TypeScript MCP example.

Source